/install akievo
Akievo — Agent Plan Mode
You have access to Akievo, a structured project management system. Use it as your persistent memory and planning layer for long-term goals. Akievo boards survive session resets — they are your source of truth.
Core Principles
- Always check before creating. At the start of every session, call
list_boardsto find existing plans before creating new ones. - One board per goal. Each major goal or project gets its own board. Prefix agent-created boards with
[Agent](e.g.,[Agent] Launch SaaS Product). - Lists are phases. Use lists to represent sequential phases or categories (e.g., "Research", "Build", "Launch", "Done").
- Cards are tasks. Each actionable step is a card. Include clear titles and descriptions.
- Respect human edits. The human may add, remove, reprioritize, or comment on cards. Always re-read the board before acting. Never undo or override human changes.
Session Start Pattern
Every time a new session begins:
- Call
list_boardsto find boards prefixed with[Agent] - If a relevant board exists, call
get_boardwith its ID to load the full state - Read the board's
project_memoryfield for context (goal, timeline, assumptions) - Identify the next unblocked, incomplete task
- Report status to the user: what's done, what's next, any blockers
Creating a New Plan
When the user describes a new goal:
- Call
list_workspacesto find available workspaces - Use
create_board_with_tasksto scaffold the entire plan in one call:- Break the goal into 3–6 phases (lists)
- Each phase gets 3–8 concrete tasks (cards)
- Add checklists for tasks with sub-steps
- Set priorities:
critical,high,medium,low - Set due dates when the user provides a timeline
- Create dependencies between tasks that have a natural order using
bulk_create_dependencies - Present the plan to the user and ask for feedback before proceeding
Working on Tasks
When executing on a plan:
- Pick the next unblocked, highest-priority incomplete card
- Work on it (using your other tools — coding, research, writing, etc.)
- Add progress updates as comments using
add_comment - When done, call
complete_cardto mark it finished - If blocked, call
block_cardwith a clear reason - Move to the next task
Updating the Plan
As work progresses, the plan may need adjustment:
- Add new tasks:
create_cardin the appropriate list - Update details:
update_cardto change title, description, priority, or due date - Reorder:
move_cardto shift tasks between phases - Add sub-tasks:
add_checklist_itemfor granular steps - Never delete cards without asking the user first
Progress Reporting
When the user asks for a status update:
- Call
get_boardto get current state - Count completed vs total cards per list
- Highlight blocked items and their reasons
- Identify upcoming due dates
- Suggest next actions
Important Safety Rules
- Never delete a board without explicit user confirmation
- Never archive cards without asking
- Always re-read the board before making changes (the human may have edited it)
- Log your work — add comments to cards explaining what you did and why
- Stay scoped — only modify boards you created or were explicitly asked to manage
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install akievo - After installation, invoke the skill by name or use
/akievo - Provide required inputs per the skill's parameter spec and get structured output
What is Akievo?
Persistent project planning for AI agents. Create, manage, and track long-term goals using structured Kanban boards that survive session resets. It is an AI Agent Skill for Claude Code / OpenClaw, with 141 downloads so far.
How do I install Akievo?
Run "/install akievo" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Akievo free?
Yes, Akievo is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Akievo support?
Akievo is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Akievo?
It is built and maintained by Akievo (@akievo); the current version is v1.0.0.